IVI Notebook

#Setup

#install.packages("tidyverse")
#install.packages("PerformanceAnalytics")
#install.packages("ggfortify")
#install.packages("fastDummies")

library(tidyverse) # core package includes following packages: tidyr, dplyr, ggplot2, readr, purrr, tibble, stringr, forcats

Warnung: vorhergehender Import ‘lifecycle::last_warnings’ durch ‘rlang::last_warnings’ während des Ladens von ‘pillar’ ersetztWarnung: vorhergehender Import ‘lifecycle::last_warnings’ durch ‘rlang::last_warnings’ während des Ladens von ‘tibble’ ersetztRegistered S3 methods overwritten by 'dbplyr':
  method         from
  print.tbl_lazy     
  print.tbl_sql      
Warnung: vorhergehender Import ‘lifecycle::last_warnings’ durch ‘rlang::last_warnings’ während des Ladens von ‘hms’ ersetzt-- Attaching packages ----------------------------------------------------------------------- tidyverse 1.3.1 --
v ggplot2 3.3.5     v purrr   0.3.4
v tibble  3.1.4     v dplyr   1.0.7
v tidyr   1.1.3     v stringr 1.4.0
v readr   2.0.1     v forcats 0.5.1
-- Conflicts -------------------------------------------------------------------------- tidyverse_conflicts() --
x dplyr::filter() masks stats::filter()
x dplyr::lag()    masks stats::lag()

library(plotly)

Warnung: Paket ‘plotly’ wurde unter R Version 4.1.3 erstelltRegistered S3 method overwritten by 'data.table':
  method           from
  print.data.table     
Registered S3 method overwritten by 'htmlwidgets':
  method           from         
  print.htmlwidget tools:rstudio

Attache Paket: ‘plotly’

Das folgende Objekt ist maskiert ‘package:ggplot2’:

    last_plot

Das folgende Objekt ist maskiert ‘package:stats’:

    filter

Das folgende Objekt ist maskiert ‘package:graphics’:

    layout

library("PerformanceAnalytics") #for correlation

Warnung: Paket ‘PerformanceAnalytics’ wurde unter R Version 4.1.3 erstelltLade nötiges Paket: xts
Warnung: Paket ‘xts’ wurde unter R Version 4.1.3 erstelltLade nötiges Paket: zoo
Warnung: Paket ‘zoo’ wurde unter R Version 4.1.3 erstellt
Attache Paket: ‘zoo’

Die folgenden Objekte sind maskiert von ‘package:base’:

    as.Date, as.Date.numeric


Attache Paket: ‘xts’

Die folgenden Objekte sind maskiert von ‘package:dplyr’:

    first, last


Attache Paket: ‘PerformanceAnalytics’

Das folgende Objekt ist maskiert ‘package:graphics’:

    legend

library(broom) # for model quantification
library(ggfortify) # for visualizing model fits

Warnung: Paket ‘ggfortify’ wurde unter R Version 4.1.3 erstellt

library(fastDummies)

Warnung: Paket ‘fastDummies’ wurde unter R Version 4.1.3 erstellt

library(dplyr)
library(ggplot2)

bike_data <- read_csv("SeoulBikeData.csv",
  show_col_types = FALSE,
  col_types = cols(Date = col_date(format = "%d/%m/%Y"),
    Seasons = col_factor(levels = c("Winter", "Spring", "Summer", "Autumn"),
                         ordered = TRUE),
    Holiday = col_factor(),
    "Functioning Day" = col_factor()
  ))

bike_data <- bike_data %>%
  mutate(day = weekdays(Date), 
         month = months(Date),
         day_time = case_when(
           Hour >= 5 & Hour < 11 ~ "Morning",
           Hour >= 11 & Hour < 15 ~ "Noon",
           Hour >= 15 & Hour < 18 ~ "Afternoon",
           Hour >= 18 & Hour < 22 ~ "Evening",
           Hour < 5 | Hour >= 22 ~ "Night")) %>%
  select(Date,month,day,Hour,day_time, Holiday, 'Rented Bike Count',everything())

bike_data$day_time <- factor(bike_data$day_time,
                             levels = c("Morning", "Noon", "Afternoon", "Evening", "Night"),ordered = TRUE)

bike_data$day <- factor(bike_data$day, 
                        levels = c("Montag", "Dienstag", "Mittwoch", "Donnerstag", "Freitag", "Samstag", "Sonntag" ))

bike_data$month <- factor(bike_data$month, 
                          levels = c("Januar", "Februar", "März", "April", "Mai", "Juni", "Juli", "August", "September", "Oktober","November", "Dezember"))

#LO1: Performance

grafik_1 <- bike_data %>%
  plot_ly(x = ~Seasons) %>%
    add_histogram(color = I("darkgreen"), opacity = 0.9) %>%
  layout(title = "Total bike count by seasons")

start <- Sys.time()
grafik_1

end <- Sys.time()
print(end - start)

Time difference of 0.473356 secs

grafik_4 <- ggplot(bike_data, aes(`Temperature` ,`Rented Bike Count`, color = `Seasons`))+
  geom_jitter(alpha = 0.3)+
  scale_fill_grey(start = 0.2, end = 0.8,na.value = "red")+
  stat_smooth(method = lm, se = FALSE, color = "red")+
  labs(
    x = "Temperature in Celsius",
    y = "Rented Bikes",
    title = "Correlation between temperature and rented bikes")+
  theme_minimal()

start <- Sys.time()
grafik_4

end <- Sys.time()
print(end - start)

Time difference of 1.329525 secs

#LO2: Dashboard design principes

Grafik 3:

bike_data %>%
  plot_ly(x = ~Seasons) %>%
    add_histogram(color = I("navy"), opacity = 0.9) %>%
  layout(title = "Total bike count by seasons")

##Grafik 4:

grafik_4 <- ggplot(bike_data, aes(`Temperature` ,`Rented Bike Count`, color = `Seasons`))+
  geom_jitter(alpha = 0.3)+
  scale_fill_grey(start = 0.2, end = 0.8,na.value = "red")+
  stat_smooth(method = lm, se = FALSE, color = "red")+
  labs(
    x = "Temperature in Celsius",
    y = "Rented Bikes",
    title = "Correlation between temperature and rented bikes")+
  theme_minimal()

ggplotly(grafik_4)

`geom_smooth()` using formula 'y ~ x'

##Grafik 5

scatter <- ggplot(bike_data,aes(x= Snowfall, y = `Rented Bike Count`))+
  geom_jitter(shape=8, (aes(color = Temperature)))+
  scale_color_gradient(low="dark blue", high= "light blue")+
  facet_wrap(~month)+
  ggtitle("Bike rental and the impact of snow")+
  theme_minimal()

ggplotly(scatter)

grafik_4 <- plot_ly() %>%
  add_trace(bike, x = ~'Hour', y = ~bike_data$'Rented Bike Count', type = 'scatter', mode = 'lines+markers', name = 'Name of Trace 1') %>%
  layout(title = 'Plot Title')

grafik_4

#LO3: #LO4: Evaluation